The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020

Abstract

This report describes the systems submitted to the first and second tracks of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020, which ranked second in both tracks. Three key points of the system pipeline are explored: (1) investigating multiple CNN architectures including ResNet, Res2Net and dual path network (DPN) to extract the x-vectors, (2) using a composite angular margin softmax loss to train the speaker models, and (3) applying score normalization and system fusion to boost the performance. Measured on the VoxSRC-20 Eval set, the best submitted systems achieve an EER of $3.808\%$ and a MinDCF of $0.1958$ in the close-condition track 1, and an EER of $3.798\%$ and a MinDCF of $0.1942$ in the open-condition track 2, respectively.

References in corpus (7)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Res2Net: A New Multi-scale Backbone Architecture
• VoxCeleb2: Deep Speaker Recognition
• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF
• BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
• VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge

Cited by in corpus (2)

• VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
• The VoxCeleb Speaker Recognition Challenge: A Retrospective